You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
With these set of parameters I would assume a bottleneck block will be created with 1/2 the channels in the bottleneck and 1 group convolution (i.e. standard convolution)
However: l.25 changes the groups to ls_group_width = ls_group_width.astype(np.int) * bottleneck_ratio => group_width = 32 making this block impossible and having the model FAIL!
Is this intentional or a bug?
Thank you very much
The text was updated successfully, but these errors were encountered:
Hi,
Thanks for a GREAT repo!
I think there might be a bug in the creation of RegnetX here:
regnet/src/regnet.py
Line 25 in 031b1b5
Why would you multiply the
group_width
by thebottleneck_ratio
?I will demonstrate through an example:
With these set of parameters I would assume a bottleneck block will be created with 1/2 the channels in the bottleneck and 1 group convolution (i.e. standard convolution)
However: l.25 changes the groups to
ls_group_width = ls_group_width.astype(np.int) * bottleneck_ratio => group_width = 32
making this block impossible and having the model FAIL!Is this intentional or a bug?
Thank you very much
The text was updated successfully, but these errors were encountered: